Spatial–temporal seizure detection with graph attention network and bi-directional LSTM architecture. (September 2022)

• Record Type: Journal Article
• Authors: He, Jiatong; Cui, Jia; Zhang, Gaobo; Xue, Mingrui; Chu, Dengyu; Zhao, Yanna
• Is Part Of: Biomedical signal processing and control. Volume 78(2022)
• Publication Date: 2022-09
• Subjects: Seizure detection -- Scalp EEG -- Deep learning -- Graph attention network -- Bi-directional LSTM; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.103908
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: The automatic detection of epileptic seizures by Electroencephalogram (EEG) can accelerate the diagnosis of the disease by neurologists, which is of incredible importance for the treatment of patients with epilepsy. However, current works on EEG-based seizure detection do not fully exploit the spatial–temporal information of EEG channels. In order to tackle this problem, we propose an automatic spatial–temporal epileptic seizure detection framework based on deep learning. Specifically, graph attention networks (GAT) are used as the front-end to extract spatial features. Thus, the topology of different EEG channels is fully exploited. Meanwhile, bi-directional long short-term memory (BiLSTM) network is used as the back-end to mine time relations and make the final decision according to the state before and after the current moment. Experiments are conducted on the CHB-MIT and the TUH datasets. Extensive experimental results demonstrate that the proposed model can effectively detect seizures from the raw EEG signals without extra feature extraction. The seizure detection accuracy on the two datasets are 98.52%, 98.02%, respectively. The performance of the model is better than or comparable to the-state-of-the-arts. Highlights: An automatic seizure detection model based on GAT and Bi-LSTM is proposed. We explore the temporal and spatial relationship between epileptic EEG channels. The proposed method has well performance on the CHB-MIT dataset and the TUH dataset.